Self-Similarity Features for Multimodal Remote Sensing Image Matching

Xiong, Xuejian; Gao, Jin; Xu, Qing; Zhang, Hongmin

doi:10.1109/jstars.2021.3131489

Cited by 24 publications

(7 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we evaluate the proposed algorithm on three multimodal remote sensing datasets and compare its performance against three state-of-the-art algorithms, namely RIFT [6], SRIF [11], and OSS [15]. For fairness, our algorithm increases the number of extracted feature points M to 2% of the total pixel number to achieve comparability with RIFT and SRIF in terms of the feature point number.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Considering the high computational overhead, our previous work designed an offset mean filtering (OMF) method to efficiently compute the SS feature. Additionally, we designed an improved maximal selfdissimilarities (IMSD) feature detector and an oriented selfsimilarity (OSS) feature descriptor for successful multimodal image matching [15]. However, the method encounters two challenges when applied to large-scale datasets.…”

Section: Introductionmentioning

confidence: 99%

“…To address these challenges, we propose a robust multimodal remote sensing image matching method that leverages enhanced OSS (EOSS) descriptor. Based on our previous work [15], we design two optimizations to enhance the performance of the OSS descriptor and incorporate a position-weighted matching (PWM) method for achieving reliable matches. Our contributions can be summarized as follows.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust Multimodal Remote Sensing Image Matching Based on Enhanced Oriented Self-Similarity Descriptor

Xiong,

Jin,

Wang

et al. 2024

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

The presence of complex geometric and radiometric differences in multimodal remote sensing images poses a significant challenge for existing image matching methods. In this letter, we propose a robust multimodal remote sensing image matching method based on an enhanced oriented self-similarity descriptor. Based on our previous oriented self-similarity descriptor, the assigned main orientations are refined by introducing a Gaussian smoothing function to improve robustness, and the redundant information is eliminated by downsampling the descriptor neighborhood to improve efficiency. Additionally, we design a position-weighted matching method to optimize the matching performance. Experimental results on three types of multimodal remote sensing image datasets comprising 75 image pairs demonstrate that the proposed method surpasses existing methods and exhibits superior robustness in achieving successful matching, with a success rate of 100 %. Our executable program and datasets are available for public download in https://github.com/Xxin08/EOSS.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Multimodal Remote Sensing Image Matching Based on Enhanced Oriented Self-Similarity Descriptor

Xiong,

Jin,

Wang

et al. 2024

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

show abstract

“…Additionally, as a pioneering work, the LSS is first designed to capture the local structural features by measuring the correlations between the central patch and its neighbors, making the descriptor more robust against modality variations. Several LSS-based descriptors have been successfully applied to multimodal image registration, including dense LSS (DLSS) [29], dense rank-based LSS (DRLSS) [30], max-index-based LSS (MLSS) [31], histogram of oriented self-similarity (HOSS) [32], pyramid features of orientated self-similarity (POSS) [33], oriented self-similarity (OSS) [34], and adjacent self-similarity (ASS) [21]. Although these PC-based and LSS-based descriptors perform well, they still have some limitations.…”

Section: Introductionmentioning

confidence: 99%

Robust Registration of Optical and SAR Images Using Multi-Orientation Relative Total Variation Structural Representation

Fan,

Xiong,

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Accurate registration of optical and synthetic aperture radar (SAR) images remains a challenging task because of the potential large modality differences across individual images. To improve the registration performance, this paper proposes a robust registration method for optical and SAR images based on a novel multi-orientation relative total variation (MORTV) structural representation. The MORTV model is designed by integrating multiple orientation strategy into the original RTV to extract the structural maps, which can capture more structural features while removing image noises and textures. Then, a novel feature descriptor called layer-wise multiscale histogram of oriented gradient (LMHOG) is constructed on the multiscale structural maps that are generated using the MORTV model with different parameters. The LMHOG can fully characterize structural features at different scales in a multilayer manner, further enhancing the robustness and distinctiveness of the descriptor without increasing its dimension. Comprehensive experiments on two large-scale optical and SAR image datasets validate that the proposed method obtains superior registration performance over several state-of-the-art methods.

show abstract

“…Wang et al [30] constructed descriptors by combining the orientation information of phase congruency with the map of maximum index, which improved the robustness of descriptors. Based on the improved maximal selfsimilarity (IMSD) feature detector and the oriented self-similarity (OSS) feature descriptor, Xiong et al [31] registered image pairs successfully. Then, an optimized offset mean filtering (OMF) method was proposed to extract adjacent self-similarity (ASS) features, which improved registration efficiency and robustness [32].…”

Section: Introductionmentioning

confidence: 99%

Optical and SAR Image Registration Based on Multi-Scale Orientated Map of Phase Congruency

et al. 2023

View full text Add to dashboard Cite

Optical and Synthetic Aperture Radar (SAR) images are highly complementary, and their registrations are a fundamental task for other remote sensing applications. Traditional feature-matching algorithms fail to solve the significant nonlinear radiation difference (NRD) caused by different sensors. To address this problem, a robust registration algorithm with the multi-scale orientated map of phase congruency (MSPCO) is proposed. First, a nonlinear diffusion scale space is established to obtain the scale invariance of feature points. Compared with the linear Gaussian scale space, the nonlinear diffusion scale space can better preserve the edge and texture information. Second, to ensure the quantity and repeatability of features, corner points and edge points are detected on the moment map of phase congruency, respectively, which is the foundation to the next feature matching. Third, the MSPCO descriptor is constructed via the orientation of phase congruency (PCO). PCO is highly robust to NRD, and the different scales of PCOs enhance the robustness of the descriptor. Finally, a feature-matching strategy based on an effective scale ratio is proposed, which reduces the number of comparisons among features and improves computational efficiency. The experimental results show that the proposed method is better than the existing feature-based methods in terms of the number of correct matches and registration accuracy. The registration accuracy is only inferior to that of the most advanced template matching method, and the accuracy difference is within 0.3 pixels, which fully demonstrates the robustness and accuracy of the proposed method in optical and SAR image registration.

show abstract

Self-Similarity Features for Multimodal Remote Sensing Image Matching

Cited by 24 publications

References 53 publications

Robust Multimodal Remote Sensing Image Matching Based on Enhanced Oriented Self-Similarity Descriptor

Robust Multimodal Remote Sensing Image Matching Based on Enhanced Oriented Self-Similarity Descriptor

Robust Registration of Optical and SAR Images Using Multi-Orientation Relative Total Variation Structural Representation

Optical and SAR Image Registration Based on Multi-Scale Orientated Map of Phase Congruency

Contact Info

Product

Resources

About